Fix Ego4D target compatibility in local baselines

easycom_head.py

@@ -278,8 +278,18 @@ def _validate_loss_inputs(
         )
 
 
-def _validated_binary_activity_targets(targets: torch.Tensor) -> torch.Tensor:
-    """Validate the four legal EasyCom/EgoSpeak three-label activity rows."""
+def _validated_binary_activity_targets(
+    targets: torch.Tensor,
+    *,
+    allow_noncanonical_binary: bool = False,
+) -> torch.Tensor:
+    """Validate three-label activity rows.
+
+    EasyCom uses four explicit activity states.  Ego4D's released target files
+    are consumed by EgoSpeak's MCE objective as binary/multi-positive weights,
+    so the compatibility path preserves any binary row instead of silently
+    rewriting it to an EasyCom state.
+    """
 
     if targets.ndim < 1 or targets.shape[-1] != NUM_CLASSES:
         raise ValueError(
@@ -291,11 +301,22 @@ def _validated_binary_activity_targets(targets: torch.Tensor) -> torch.Tensor:
     rounded = targets.round()
     if not torch.allclose(targets, rounded, atol=1e-6, rtol=0.0):
         raise ValueError("Activity targets must contain only binary 0/1 values")
-    expected_background = (rounded[..., 1:].sum(dim=-1) == 0).to(rounded.dtype)
-    if not torch.equal(rounded[..., 0], expected_background):
+    expected_background = rounded[..., 1:].sum(dim=-1) == 0
+    valid = rounded[..., 0].bool() == expected_background
+    if allow_noncanonical_binary:
+        return rounded
+    if not bool(valid.all()):
+        invalid = torch.unique(rounded[~valid].reshape(-1, NUM_CLASSES), dim=0)
+        invalid_rows = ", ".join(
+            str([int(value) for value in row.tolist()])
+            for row in invalid[:8]
+        )
+        if len(invalid) > 8:
+            invalid_rows += ", ..."
         raise ValueError(
             "Activity targets must be one of [1,0,0], [0,1,0], "
-            "[0,0,1], or [0,1,1]"
+            "[0,0,1], or [0,1,1]; observed invalid "
+            f"row(s): {invalid_rows}"
         )
     return rounded
 
@@ -799,7 +820,13 @@ def load_session_data(
             f"{target_path}"
         )
     targets = torch.from_numpy(np.asarray(target_array, dtype=np.float32))
-    _validated_binary_activity_targets(targets)
+    try:
+        _validated_binary_activity_targets(
+            targets,
+            allow_noncanonical_binary=dataset == "ego4d",
+        )
+    except ValueError as error:
+        raise ValueError(f"{error}: {target_path}") from error
     if len(label_indices) and int(label_indices[-1]) >= len(targets):
         raise ValueError(
             f"Last label index {int(label_indices[-1])} exceeds target length "
@@ -823,6 +850,20 @@ def load_session_data(
             "video_sampling_grid",
         )
     }
+    expected_background = targets[:, 1:].sum(dim=-1) == 0
+    canonical_rows = targets[:, 0].bool() == expected_background
+    unique_rows, row_counts = torch.unique(
+        targets.to(dtype=torch.int64),
+        dim=0,
+        return_counts=True,
+    )
+    metadata["num_noncanonical_target_rows"] = int(
+        (~canonical_rows).sum().item()
+    )
+    metadata["target_row_pattern_counts"] = {
+        "".join(str(int(value)) for value in row.tolist()): int(count)
+        for row, count in zip(unique_rows, row_counts)
+    }
     local = None
     if local_feature_root is not None:
         from local_turn_features import load_local_features